| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MSVD | MaMMUT | CIDEr195.6 | 128 | 2d ago | |
| MSR-VTT (test) | ComHeat | CIDEr104.2 | 121 | 2d ago | |
| MSVD (test) | AdaCM² | CIDEr189.4 | 111 | 2d ago | |
| Youcook2 | VALUE | METEOR40.4 | 104 | 2d ago | |
| MSRVTT | mPLUG-2 | CIDEr80.3 | 101 | 2d ago | |
| YouCook II (val) | MV-GPT | CIDEr221 | 98 | 2d ago | |
| MSRVTT (test) | HierarQ | CIDEr80.5 | 61 | 2d ago | |
| MSRVTT | mPLUG-2 | CIDEr80.3 | 61 | 3d ago | |
| VATEX (test) | Flamingo | CIDEr84.2 | 59 | 2d ago | |
| VATEX | VAST | CIDEr99.5 | 46 | 2d ago | |
| YouCook2 (test) | UniVL + MELTR | CIDEr190 | 42 | 2d ago | |
| VDC | VideoZoomer | Short Accuracy49.2 | 28 | 3d ago | |
| VATEX (public test) | GIT2 | CIDEr94.5 | 24 | 2d ago | |
| Vript-HAL (full) | Vriptor-S | F1 Score58.3 | 22 | 3d ago | |
| TVC (val) | GIT2 | CIDEr66.1 | 22 | 2d ago | |
| ActivityNet Captions (val) | PRISM | METEOR20.04 | 22 | 3d ago | |
| Molmo2 CapTest (test) | F1 Score56.6 | 21 | 3d ago | ||
| MCTS-VCB | Appearance Description Precision84.9 | 21 | 3d ago | ||
| MSRVTT (full) | GiT2 | CIDEr75.9 | 20 | 3d ago | |
| E.T. Bench-Captioning (test) | GPT-4o | DVC F146.9 | 16 | 3d ago | |
| TVC (test) | COSA (1.2B) | CIDEr70.7 | 16 | 3d ago | |
| TVC | VAST | CIDEr74.1 | 15 | 3d ago | |
| VATEX online evaluation (test) | SWINBERT | CIDEr73 | 15 | 3d ago | |
| VATEX (private test) | GIT2 | CIDEr96.6 | 14 | 2d ago | |
| MSVC | Gemini 1.5 Pro | Correctness3.67 | 13 | 3d ago |